maxxime's picture
First Push
8b800a0 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.899291455745697,
"min": 0.899291455745697,
"max": 2.8300554752349854,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8546.8662109375,
"min": 8546.8662109375,
"max": 28889.205078125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.552804946899414,
"min": 0.5339867472648621,
"max": 12.552804946899414,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2447.796875,
"min": 103.59342956542969,
"max": 2512.974365234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06623454278964988,
"min": 0.06309502133323501,
"max": 0.07704029679321228,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2649381711585995,
"min": 0.25238008533294004,
"max": 0.3548807108754238,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21564902555124432,
"min": 0.1719523592128455,
"max": 0.27582672399048713,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8625961022049773,
"min": 0.687809436851382,
"max": 1.3046994659246185,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.75,
"min": 4.545454545454546,
"max": 24.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1089.0,
"min": 200.0,
"max": 1355.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.75,
"min": 4.545454545454546,
"max": 24.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1089.0,
"min": 200.0,
"max": 1355.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1785874632",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/content/miniconda/envs/py310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1785875131"
},
"total": 499.237630416,
"count": 1,
"self": 0.4813321999997697,
"children": {
"run_training.setup": {
"total": 0.029184159000124055,
"count": 1,
"self": 0.029184159000124055
},
"TrainerController.start_learning": {
"total": 498.7271140570001,
"count": 1,
"self": 0.4932915229912851,
"children": {
"TrainerController._reset_env": {
"total": 3.015227456000048,
"count": 1,
"self": 3.015227456000048
},
"TrainerController.advance": {
"total": 495.1314979500087,
"count": 18192,
"self": 0.5258383690381834,
"children": {
"env_step": {
"total": 370.498674459993,
"count": 18192,
"self": 290.42596843698516,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.76861755000573,
"count": 18192,
"self": 1.441448960999196,
"children": {
"TorchPolicy.evaluate": {
"total": 78.32716858900653,
"count": 18192,
"self": 78.32716858900653
}
}
},
"workers": {
"total": 0.3040884730021389,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 496.5586064460033,
"count": 18192,
"is_parallel": true,
"self": 243.26165688600963,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054929320001519955,
"count": 1,
"is_parallel": true,
"self": 0.003975294000156282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015176379999957135,
"count": 10,
"is_parallel": true,
"self": 0.0015176379999957135
}
}
},
"UnityEnvironment.step": {
"total": 0.07235379200005809,
"count": 1,
"is_parallel": true,
"self": 0.0005877709998003411,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037517999999181484,
"count": 1,
"is_parallel": true,
"self": 0.00037517999999181484
},
"communicator.exchange": {
"total": 0.06742044700013139,
"count": 1,
"is_parallel": true,
"self": 0.06742044700013139
},
"steps_from_proto": {
"total": 0.003970394000134547,
"count": 1,
"is_parallel": true,
"self": 0.0003470450001259451,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003623349000008602,
"count": 10,
"is_parallel": true,
"self": 0.003623349000008602
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.29694955999366,
"count": 18191,
"is_parallel": true,
"self": 11.257673140954694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.979289868020487,
"count": 18191,
"is_parallel": true,
"self": 5.979289868020487
},
"communicator.exchange": {
"total": 195.12602212200613,
"count": 18191,
"is_parallel": true,
"self": 195.12602212200613
},
"steps_from_proto": {
"total": 40.93396442901235,
"count": 18191,
"is_parallel": true,
"self": 7.414764593015661,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.51919983599669,
"count": 181910,
"is_parallel": true,
"self": 33.51919983599669
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.10698512097747,
"count": 18192,
"self": 0.6340856689798784,
"children": {
"process_trajectory": {
"total": 25.380496326996536,
"count": 18192,
"self": 24.894578137996632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4859181889999036,
"count": 4,
"self": 0.4859181889999036
}
}
},
"_update_policy": {
"total": 98.09240312500106,
"count": 90,
"self": 39.51663093598813,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.57577218901292,
"count": 4587,
"self": 58.57577218901292
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.570001111569582e-07,
"count": 1,
"self": 9.570001111569582e-07
},
"TrainerController._save_models": {
"total": 0.08709617099998468,
"count": 1,
"self": 0.0008169039999756933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08627926700000899,
"count": 1,
"self": 0.08627926700000899
}
}
}
}
}
}
}